purecontext

A set of Cursor rules for using PureContext MCP, a code-navigation service, to find and inspect code through targeted searches.

In plain words
What is it for?
Navigating repositories, finding functions or classes, reading selected implementations, locating references, and assessing change impact before editing risky code.
Why use it?
It prevents reading whole files unnecessarily and provides a fixed process for locating symbols, understanding dependencies, and checking what a change may affect.

Cursor rule for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/goranocokoljic/pure-context/purecontext
Clone the repo
git clone --depth 1 https://github.com/goranocokoljic/pure-context

Made for: Cursor.

Per session 667 This file is loaded in full into every session.
When invoked 667 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00667 $0.00667
Opus 5 $0.00333 $0.00333
Sonnet 5 $0.00133 $0.00133
Haiku 4.5 $0.00067 $0.00067

Measured 2d ago against content hash df436e39c466, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

purecontext scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/rules/purecontext.mdc · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

hmmm--- description: PureContext MCP code navigation rules alwaysApply: true

PureContext MCP — Code Navigation

Always use PureContext MCP tools for code navigation. Never read entire files to find code.

Mandatory workflow

  1. Start every session: list_repos() → get repoId (required for all tools)
  2. Find code by name: search_symbols → read summary and signature → only call get_symbol_source for symbols you will actually edit
  3. Find code by behaviour: search_semantic for conceptual queries; search_text for literals/comments

Pick the right tool

I need to… Use
Find a function/class/method by name search_symbols
Find code by what it does (meaning) search_semantic
Find a literal string, comment, or config value search_text
Read a symbol's implementation get_symbol_source
Read a non-symbol file region (imports, config) get_file_content
Survey one file / the whole project get_file_outline / get_repo_outline
Know what breaks if I change a symbol get_blast_radius
Find every call site of a symbol find_references
See the callers/callees tree get_call_hierarchy
Judge how risky a symbol is to change get_symbol_risk
Find files that change together with this one get_co_change
Pre-flight a rename / delete / move check_rename_safe / check_delete_safe / check_move_safe
Find exported symbols with no tests find_untested_symbols
Codebase health score / debt report health_radar / get_debt_report

Before editing risky code

Before broad or automated edits to an unfamiliar symbol, check get_symbol_risk (composite churn + centrality + complexity + test-gap + co-change, banded low/review/high). For a high symbol, inspect its callers (get_blast_radius) and its historical co-changers (get_co_change) first — co-changing files are the second-order edits the import graph can't show you. search_symbols and get_symbol_source accept includeRisk: true to attach a compact { band, riskScore } inline.

Read the full file on GitHub · 48 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 48 lines · 667 tokens per session scan A df436e39c466

Subscribe to this mod's changes

purecontext is a cursor rule published in the GitHub repository goranocokoljic/pure-context (7 stars, last pushed 5d ago), licensed MIT. It adds 667 tokens to every session, about $0.0033 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.